Audio MCP Server
Provides audio input and output capabilities for AI assistants.
Audio MCP Server
An MCP (Model Context Protocol) server that provides audio input/output capabilities for AI assistants like Claude. This server enables Claude to interact with your computer's audio system, including recording from microphones and playing audio through speakers.
Features
- List Audio Devices: View all available microphones and speakers on your system
- Record Audio: Capture audio from any microphone with customizable duration and quality
- Playback Recordings: Play back your most recent recording
- Audio File Playback: Play audio files through your speakers
- Text-to-Speech: (Placeholder for future implementation)
Requirements
- Python 3.8 or higher
- Audio input/output devices on your system
Installation
Installing via Smithery
To install Audio Interface Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @GongRzhe/Audio-MCP-Server --client claude
Manual Installation
- Clone this repository or download the files to your computer:
git clone https://github.com/GongRzhe/Audio-MCP-Server.git
cd Audio-MCP-Server
- Create a virtual environment and install dependencies:
# Windows
python -m venv .venv
.venv\Scripts\activate
pip install -r requirements.txt
# macOS/Linux
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
- Or use the included setup script to automate installation:
python setup_mcp.py
Configuration
Claude Desktop Configuration
To use this server with Claude Desktop, add the following to your Claude Desktop configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"audio-interface": {
"command": "/path/to/your/.venv/bin/python",
"args": [
"/path/to/your/audio_server.py"
],
"env": {
"PYTHONPATH": "/path/to/your/audio-mcp-server"
}
}
}
}
Replace the paths with the actual paths on your system. The setup script will generate this configuration for you.
Usage
After setting up the server, restart Claude Desktop. You should see a hammer icon in the input box, indicating that tools are available.
Try asking Claude:
- "What microphones and speakers are available on my system?"
- "Record 5 seconds of audio from my microphone."
- "Play back the audio recording."
- "Play an audio file from my computer."
Available Tools
list_audio_devices
Lists all available audio input and output devices on your system.
record_audio
Records audio from your microphone.
Parameters:
duration: Recording duration in seconds (default: 5)sample_rate: Sample rate in Hz (default: 44100)channels: Number of audio channels (default: 1)device_index: Specific input device index to use (default: system default)
play_latest_recording
Plays back the most recently recorded audio.
play_audio
Placeholder for text-to-speech functionality.
Parameters:
text: The text to convert to speechvoice: The voice to use (default: "default")
play_audio_file
Plays an audio file through your speakers.
Parameters:
file_path: Path to the audio filedevice_index: Specific output device index to use (default: system default)
Troubleshooting
No devices found
If no audio devices are found, check:
- Your microphone and speakers are properly connected
- Your operating system recognizes the devices
- You have the necessary permissions to access audio devices
Playback issues
If audio playback isn't working:
- Check your volume settings
- Ensure the correct output device is selected
- Try restarting the Claude Desktop application
Server connectivity
If Claude can't connect to the server:
- Verify your configuration paths are correct
- Ensure Python and all dependencies are installed
- Check Claude's logs for error messages
License
MIT
Acknowledgments
- Built using the Model Context Protocol
- Uses sounddevice and soundfile for audio processing
Note: This server provides tools that can access your microphone and speakers. Always review and approve tool actions before they execute.
İlgili Sunucular
Ghost MCP
Interact with the Ghost blogging platform using the Model Context Protocol (MCP) with Server-Sent Events (SSE) support.
Apple Mail MCP
Fast MCP server for Apple Mail with batch JXA (87x faster) and FTS5 search index (700-3500x faster).
Tidio
Connect Tidio with your website via MCP. Embed the widget without exiting your programming environment.
Discord MCP Server
Interact with Discord channels to send and read messages using the Discord API.
mail-mcp
Most email MCP servers only read from IMAP. mail-mcp does everything: 30 tools for reading, searching, sending, replying, forwarding, and bulk operations across IMAP, SMTP, Microsoft Graph API, and Exchange Web Services. Multi-account, native OAuth2, built in Rust. Works with Gmail, Microsoft 365, Hotmail/Outlook.com, Zoho, and any standard IMAP/SMTP server.
FastAlert MCP Server
Official Model Context Protocol (MCP) server for FastAlert. This server allows AI agents (like Claude, ChatGPT, and Cursor) to list of your channels and send notifications directly through the FastAlert API.
BGG MCP
BGG MCP enables AI tools to interact with the BoardGameGeek API.
Telnyx
Official Telnyx remote MCP server for AI agents.
Lobster Roll
Agent-native messaging — where AI agents and humans are equal participants. Open source, self-hostable, MCP-ready.
mcp-server-unipile
95-tool MCP server for the Unipile unified API — messaging (LinkedIn, WhatsApp, Instagram, Telegram), email (Gmail, Outlook), calendar, LinkedIn search (people, companies, posts, jobs), profile management, connections, InMail, and webhooks.